From: Dennis Dalessandro <dennis.dalessandro@intel.com>
To: dledford@redhat.com
Cc: linux-rdma@vger.kernel.org,
Mike Marciniszyn <mike.marciniszyn@intel.com>,
stable@vger.kernel.org
Subject: [PATCH 11/20] IB/hfi1: Prevent kernel QP post send hard lockups
Date: Sun, 09 Apr 2017 10:16:35 -0700 [thread overview]
Message-ID: <20170409171633.10579.64026.stgit@scvm10.sc.intel.com> (raw)
In-Reply-To: <20170409171329.10579.92775.stgit@scvm10.sc.intel.com>
From: Mike Marciniszyn <mike.marciniszyn@intel.com>
The driver progress routines can call cond_resched() when
a timeslice is exhausted and irqs are enabled.
If the ULP had been holding a spin lock without disabling irqs and
the post send directly called the progress routine, the cond_resched()
could yield allowing another thread from the same ULP to deadlock
on that same lock.
Correct by replacing the current hfi1_do_send() calldown with a unique
one for post send and adding an argument to hfi1_do_send() to indicate
that the send engine is running in a thread. If the routine is not
running in a thread, avoid calling cond_resched().
CC: <stable@vger.kernel.org> # 4.7.x-
Fixes: Commit 831464ce4b74 ("IB/hfi1: Don't call cond_resched in atomic mode when sending packets")
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
---
drivers/infiniband/hw/hfi1/ruc.c | 26 ++++++++++++++++----------
drivers/infiniband/hw/hfi1/verbs.c | 4 ++--
drivers/infiniband/hw/hfi1/verbs.h | 6 ++++--
3 files changed, 22 insertions(+), 14 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 879eb9b..ccf8d80 100644
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -1,5 +1,5 @@
/*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
@@ -784,23 +784,29 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
/* when sending, force a reschedule every one of these periods */
#define SEND_RESCHED_TIMEOUT (5 * HZ) /* 5s in jiffies */
+void hfi1_do_send_from_rvt(struct rvt_qp *qp)
+{
+ hfi1_do_send(qp, false);
+}
+
void _hfi1_do_send(struct work_struct *work)
{
struct iowait *wait = container_of(work, struct iowait, iowork);
struct rvt_qp *qp = iowait_to_qp(wait);
- hfi1_do_send(qp);
+ hfi1_do_send(qp, true);
}
/**
* hfi1_do_send - perform a send on a QP
* @work: contains a pointer to the QP
+ * @in_thread: true if in a workqueue thread
*
* Process entries in the send work queue until credit or queue is
* exhausted. Only allow one CPU to send a packet per QP.
* Otherwise, two threads could send packets out of order.
*/
-void hfi1_do_send(struct rvt_qp *qp)
+void hfi1_do_send(struct rvt_qp *qp, bool in_thread)
{
struct hfi1_pkt_state ps;
struct hfi1_qp_priv *priv = qp->priv;
@@ -868,8 +874,10 @@ void hfi1_do_send(struct rvt_qp *qp)
qp->s_hdrwords = 0;
/* allow other tasks to run */
if (unlikely(time_after(jiffies, timeout))) {
- if (workqueue_congested(cpu,
- ps.ppd->hfi1_wq)) {
+ if (!in_thread ||
+ workqueue_congested(
+ cpu,
+ ps.ppd->hfi1_wq)) {
spin_lock_irqsave(
&qp->s_lock,
ps.flags);
@@ -882,11 +890,9 @@ void hfi1_do_send(struct rvt_qp *qp)
*ps.ppd->dd->send_schedule);
return;
}
- if (!irqs_disabled()) {
- cond_resched();
- this_cpu_inc(
- *ps.ppd->dd->send_schedule);
- }
+ cond_resched();
+ this_cpu_inc(
+ *ps.ppd->dd->send_schedule);
timeout = jiffies + (timeout_int) / 8;
}
spin_lock_irqsave(&qp->s_lock, ps.flags);
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 7f49719..e112762 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1,5 +1,5 @@
/*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
@@ -1816,7 +1816,7 @@ int hfi1_register_ib_device(struct hfi1_devdata *dd)
dd->verbs_dev.rdi.driver_f.qp_priv_free = qp_priv_free;
dd->verbs_dev.rdi.driver_f.free_all_qps = free_all_qps;
dd->verbs_dev.rdi.driver_f.notify_qp_reset = notify_qp_reset;
- dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send;
+ dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send_from_rvt;
dd->verbs_dev.rdi.driver_f.schedule_send = hfi1_schedule_send;
dd->verbs_dev.rdi.driver_f.schedule_send_no_lock = _hfi1_schedule_send;
dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = get_pmtu_from_attr;
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 6c549e7..46b00ed 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -1,5 +1,5 @@
/*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
@@ -355,7 +355,9 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
void _hfi1_do_send(struct work_struct *work);
-void hfi1_do_send(struct rvt_qp *qp);
+void hfi1_do_send_from_rvt(struct rvt_qp *qp);
+
+void hfi1_do_send(struct rvt_qp *qp, bool in_thread);
void hfi1_send_complete(struct rvt_qp *qp, struct rvt_swqe *wqe,
enum ib_wc_status status);
next prev parent reply other threads:[~2017-04-09 17:16 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-09 17:15 [PATCH 00/20] IB/hfi1,rdmavt,core: Patches for-next Dennis Dalessandro
2017-04-09 17:15 ` [PATCH 01/20] IB/core: If the MGID/MLID pair is not on the list return an error Dennis Dalessandro
2017-04-09 17:15 ` [PATCH 04/20] IB/core: For multicast functions, verify that LIDs are multicast LIDs Dennis Dalessandro
2017-04-15 15:01 ` Leon Romanovsky
2017-04-09 17:16 ` Dennis Dalessandro [this message]
2017-04-09 17:17 ` [PATCH 20/20] IB/hfi1: Use bool in process_ecn Dennis Dalessandro
2017-04-28 17:45 ` [PATCH 00/20] IB/hfi1,rdmavt,core: Patches for-next Doug Ledford
2017-04-28 17:50 ` Dennis Dalessandro
2017-04-28 18:09 ` Doug Ledford
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170409171633.10579.64026.stgit@scvm10.sc.intel.com \
--to=dennis.dalessandro@intel.com \
--cc=dledford@redhat.com \
--cc=linux-rdma@vger.kernel.org \
--cc=mike.marciniszyn@intel.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).